Loading...
Loading...
Found 57 Skills
Prompt design patterns for LLMs including few-shot, chain-of-thought, structured output, and injection defense. Use when crafting prompts, optimizing LLM outputs, or building prompt-based features.
Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework
Create PydanticAI agents with type-safe dependencies, structured outputs, and proper configuration. Use when building AI agents, creating chat systems, or integrating LLMs with Pydantic validation.
Fetch the current top Hacker News stories and return agent-friendly structured results. Use this whenever the user explicitly asks about Hacker News or HN, and also when they ask for today's developer, startup, YC, or tech-community hot stories where Hacker News is a strong default source.
Dispatches many independent items in parallel: create a table, fan out to subagents, aggregate results. One row = one unit of work.
INVOKE THIS SKILL when you need human-in-the-loop approval, custom middleware, or structured output. Covers HumanInTheLoopMiddleware for human approval of dangerous tool calls, creating custom middleware with hooks, Command resume patterns, and structured output with Pydantic/Zod.
Use this skill when crafting LLM prompts, implementing chain-of-thought reasoning, designing few-shot examples, building RAG pipelines, or optimizing prompt performance. Triggers on prompt design, system prompts, few-shot learning, chain-of-thought, prompt chaining, RAG, retrieval-augmented generation, prompt templates, structured output, and any task requiring effective LLM interaction patterns.
INTERNAL sub-agent for blind 9-dimensional rubric scoring. **NOT a user-facing skill — do NOT invoke from the main conversation.** It is called via the Task tool by cheat-score / cheat-predict / cheat-bump to generate a context-isolated score for a script. It ONLY accepts script_path + rubric_notes_path; any other input will be refused. It outputs strict JSON: 9 dimensions × {score 0-5, confidence enum, one-line reason}. **It strictly refuses to read** .cheat-state.json, predictions/*, retro sections, or any content that may leak post-publish data. This is Channel B in the 3-channel calibration model (A=main, B=blind sub-agent, C=cross-model).
Engineer effective LLM prompts using zero-shot, few-shot, chain-of-thought, and structured output techniques. Use when building LLM applications requiring reliable outputs, implementing RAG systems, creating AI agents, or optimizing prompt quality and cost. Covers OpenAI, Anthropic, and open-source models with multi-language examples (Python/TypeScript).
Build agent-friendly CLIs for Eve-compatible apps. Wrap REST APIs with domain commands, auto-auth, structured errors, and --json output. Agents use CLIs instead of curl/fetch.
Expert guidance for building production-grade AI agents and workflows using Pydantic AI (the `pydantic_ai` Python library). Use this skill whenever the user is: writing, debugging, or reviewing any Pydantic AI code; asking how to build AI agents in Python with Pydantic; asking about Agent, RunContext, tools, dependencies, structured outputs, streaming, multi-agent patterns, MCP integration, or testing with Pydantic AI; or migrating from LangChain/LlamaIndex to Pydantic AI. Trigger even for vague requests like "help me build an AI agent in Python" or "how do I add tools to my LLM app" — Pydantic AI is very likely what they need.
Design Pydantic models and LLM prompt templates for structured extraction pipelines. Use when creating, editing, or reviewing Pydantic models that serve as LLM output schemas, or when writing prompt templates that pair with those models. Trigger: "pydantic model", "structured output", "extraction schema", "LLM output model", "schema design".